COMIC: Agentic Sketch Comedy Generation
2026-03-11 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial IntelligenceComputation and LanguageMultiagent SystemsNeural and Evolutionary Computing
AI summaryⓘ
The authors created an AI system that automatically makes short funny videos like those on shows such as Saturday Night Live. Their system uses different AI agents that act like people in a real comedy studio, working together to come up with and improve funny ideas. They also developed a way for the AI to judge humor by learning from popular comedy videos on YouTube. Their tests show that the AI can create videos almost as good as professional ones and leads in video generation technology.
AI systemcomedy video generationlarge language modelshumor evaluationYouTube datasetiterative improvementsketch comedyvideo generationagent-based modeling
Authors
Susung Hong, Brian Curless, Ira Kemelmacher-Shlizerman, Steve Seitz
Abstract
We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting with character references, the system employs a population of agents loosely based on real production studio roles, structured to optimize the quality and diversity of ideas and outputs through iterative competition, evaluation, and improvement. A key contribution is the introduction of LLM critics aligned with real viewer preferences through the analysis of a corpus of comedy videos on YouTube to automatically evaluate humor. Our experiments show that our framework produces results approaching the quality of professionally produced sketches while demonstrating state-of-the-art performance in video generation.